2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR)最新文献_第3页

Segmentation of Unconstrained Handwritten Hindi Words Using Polygonal Approximation 基于多边形逼近的无约束手写体印地语词分割

2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR) Pub Date : 2016-10-01 DOI: 10.1109/ICFHR.2016.0039

Kapil K. Upreti, Soumen Bag

{"title":"Segmentation of Unconstrained Handwritten Hindi Words Using Polygonal Approximation","authors":"Kapil K. Upreti, Soumen Bag","doi":"10.1109/ICFHR.2016.0039","DOIUrl":"https://doi.org/10.1109/ICFHR.2016.0039","url":null,"abstract":"Segmentation of unconstrained handwritten words into characters in an optically scanned document image data is an essential task and presents challenges to researchers with a wide variety of handwritings, large varieties of pen-types, poor image quality, and a lack of ordering information of strokes. This paper contributes methods for accurate full segmentation of Hindi word images into constituent characters and modifiers. It follows the polygonal approximation approach for the segmentation, and makes use of structural properties along with directional measures to determine segmentation points in Hindi word images. The main methodological contribution of this paper is the use of polygonal approximation technique for word segmentation which is based on certain structural properties of Hindi language. Second focus of this work lies on the fact that segmentation is done without removal of shirorekha which eliminates the complexities present in earlier works. Experiments on real-world data show that our novel method is always competitive and results in more top performances than any of the other measures.","PeriodicalId":194844,"journal":{"name":"2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR)","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123222775","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 5

Robust Output Modeling in Bag-of-Features HMMs for Handwriting Recognition 面向手写识别的特征袋hmm鲁棒输出建模

2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR) Pub Date : 2016-10-01 DOI: 10.1109/ICFHR.2016.0047

Leonard Rothacker, G. Fink

引用次数: 7

A Handwritten Chinese Character Recognition Method Combining Sub-structure Recognition 结合子结构识别的手写体汉字识别方法

2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR) Pub Date : 2016-10-01 DOI: 10.1109/ICFHR.2016.0101

Yuanping Zhu, X. An, Kuang Zhang

引用次数: 2

Scribble Based Interactive Page Layout Segmentation Using Gabor Filter 基于涂鸦的交互式页面布局分割使用Gabor过滤器

2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR) Pub Date : 2016-10-01 DOI: 10.1109/ICFHR.2016.0016

M. Kassis, Jihad El-Sana

引用次数: 13

A Human in the Loop Approach to Historical Handwritten Documents Transcription 人类在循环的方法，以历史手写文件转录

2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR) Pub Date : 2016-10-01 DOI: 10.1109/ICFHR.2016.0051

Adolfo Santoro, Antonio Parziale, A. Marcelli

引用次数: 7

Deep LSTM Networks for Online Chinese Handwriting Recognition 用于中文手写识别的深度LSTM网络

2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR) Pub Date : 2016-10-01 DOI: 10.1109/ICFHR.2016.0059

Li Sun, Tonghua Su, Ce Liu, Ruigang Wang

{"title":"Deep LSTM Networks for Online Chinese Handwriting Recognition","authors":"Li Sun, Tonghua Su, Ce Liu, Ruigang Wang","doi":"10.1109/ICFHR.2016.0059","DOIUrl":"https://doi.org/10.1109/ICFHR.2016.0059","url":null,"abstract":"Currently two heavy burdens are borne in online Chinese handwriting recognition: a large-scale training data needs to be annotated with the boundaries of each character and effective features should be handcrafted by domain experts. To relieve such issues, the paper presents a novel end-to-end recognition method based on recurrent neural networks. A mixture architecture of deep bidirectional Long Short-Term Memory (LSTM) layers and feed forward subsampling layers is used to encode the long contextual history trajectories. The Connectionist Temporal Classification (CTC) objective function makes it possible to train the model without providing alignment information between input trajectories and output strings. During decoding, a modified CTC beam search algorithm is devised to integrate the linguistic constraints wisely. Our method is evaluated both on test set and competition set of CASIA-OLHWDB 2. x. Comparing with state-of-the-art methods, over 30% relative error reductions are observed on test set in terms of both correct rate and accurate rate. Even to the more challenging competition set, better results can be achieved by our method if the out-of-vocabulary problem can be ignored.","PeriodicalId":194844,"journal":{"name":"2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131491701","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 29

Handwritten Text Recognition for Bengali 孟加拉文手写文本识别

2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR) Pub Date : 2016-10-01 DOI: 10.1109/ICFHR.2016.0105

Joan Andreu Sánchez, U. Pal

引用次数: 3

DNN-HMM for Large Vocabulary Mongolian Offline Handwriting Recognition 基于DNN-HMM的大词汇蒙古语离线手写识别

2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR) Pub Date : 2016-10-01 DOI: 10.1109/ICFHR.2016.0026

Fan Daoerji, Gao Guang-lai

{"title":"DNN-HMM for Large Vocabulary Mongolian Offline Handwriting Recognition","authors":"Fan Daoerji, Gao Guang-lai","doi":"10.1109/ICFHR.2016.0026","DOIUrl":"https://doi.org/10.1109/ICFHR.2016.0026","url":null,"abstract":"In this paper, we propose a large vocabulary Mongolian offline handwriting recognition system, using hidden Markov models (HMMs)-deep neural networks (DNN) hybrid architectures which shows superior performance on auto speech recognize (ASR) tasks. We select 50 sub-characters from all shape of Mongolian letters as the smallest modeling unit. First, a set of intensity features are extracted from each of the segmented word, which is based on a sliding window moving across each word image. Then, Multiple contextdependent Gaussian mixture model (GMM)-HMMs are trained by the features. At last a DNN which have 4 hidden layers are trained as a frame classifier, where the class labels are state labels assigned to each input frame through forced alignment using the context-dependent model. In order to validate the proposed model, extensive experiments were carried out using the MHW database which contains 100,000 handwritten words in training set, 5,000 in test set I and 14,085 in Test set II. The DNN-HMM w hich is trained on raw image pixels yields best performance on Test set I with an accuracy of 97.61% and on Test set II with an accuracy of 94.14%.","PeriodicalId":194844,"journal":{"name":"2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR)","volume":"384 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122438514","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 7

Writer Code Based Adaptation of Deep Neural Network for Offline Handwritten Chinese Text Recognition 基于Writer代码的深度神经网络自适应离线手写中文文本识别

2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR) Pub Date : 2016-10-01 DOI: 10.1109/ICFHR.2016.0106

Zirui Wang, Jun Du

{"title":"Writer Code Based Adaptation of Deep Neural Network for Offline Handwritten Chinese Text Recognition","authors":"Zirui Wang, Jun Du","doi":"10.1109/ICFHR.2016.0106","DOIUrl":"https://doi.org/10.1109/ICFHR.2016.0106","url":null,"abstract":"Recently, we propose deep neural network based hidden Markov models (DNN-HMMs) for offline handwritten Chinese text recognition. In this study, we design a novel writer code based adaptation on top of the DNN-HMM to further improve the accuracy via a customized recognizer. The writer adaptation is implemented by incorporating the new layers with the original input or hidden layers of the writer-independent DNN. These new layers are driven by the so-called writer code, which guides and adapts the DNN-based recognizer with the writer information. In the training stage, the writer-aware layers are jointly learned with the conventional DNN layers in an alternative manner. In the recognition stage, with the initial recognition results from the first-pass decoding with the writer-independent DNN, an unsupervised adaptation is performed to generate the writer code via the cross-entropy criterion for the subsequent second-pass decoding. The experiments on the most challenging task of ICDAR 2013 Chinese handwriting competition show that our proposed adaptation approach can achieve consistent and significant improvements of recognition accuracy over a highperformance writer-independent DNN-HMM based recognizer across all 60 writers, yielding a relative character error rate reduction of 23.62% in average.","PeriodicalId":194844,"journal":{"name":"2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128344058","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 12

Semi-incremental Recognition of Online Handwritten Mathematical Expressions 在线手写数学表达式的半增量识别

2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR) Pub Date : 2016-10-01 DOI: 10.1109/ICFHR.2016.0057

K. Phan, A. D. Le, M. Nakagawa

引用次数: 7